Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Gemini 2.0 Flash Exp vs InternVL2.5-78B

Google · released

Wins 1 of 1 area

Images and charts

OpenGVLab

Wins 0 of 1 area

—

Gemini 2.0 Flash Exp is the stronger all-rounder.

Scores updated · 11 tests both models report · How we compare

Where each one wins

Tests won in each of the one area where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.

The biggest differences

The tests each model wins by the widest margin, up to three each. Scores are out of 100.

Where Gemini 2.0 Flash Exp pulls ahead

  • Harder college exam questions with imagesMMMU-Pro+9.7points aheadGemini 2.0 Flash Exp57InternVL2.5-78B47.3
  • Math problems shown in pictures and chartsMathVista+4.7points aheadGemini 2.0 Flash Exp73.1InternVL2.5-78B68.4
  • College exam questions with charts, maps and diagramsMMMU+4.1points aheadGemini 2.0 Flash Exp70.6InternVL2.5-78B66.5

Where InternVL2.5-78B pulls ahead

No clear win on a test scored out of 100.

Every test, side by side

All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.

Images and chartsGemini 2.0 Flash Exp
  • MMMU-ProGemini 2.0 Flash Exp by 9.75747.3+9.7
  • MathVistaGemini 2.0 Flash Exp by 4.773.168.4+4.7
  • MMMUGemini 2.0 Flash Exp by 4.170.666.5+4.1
  • OCRBenchtie84.684.7tie

Full images and charts ranking

Other results7 tests, not counted

Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.

Questions people ask

Which is better, Gemini 2.0 Flash Exp or InternVL2.5-78B?

Gemini 2.0 Flash Exp wins the one area where both have results: images and charts. InternVL2.5-78B wins none.

How do you compare the two?

We use the 11 benchmark tests both models have published scores on. The verdict counts the 4 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.